Fuxin Li, Assistant Professor
Electrical Engineering and Computer Science
Oregon State University
In this talk, I will talk about some of our recent work in reforming the well-known recurrent and convolutional networks. In the first part, I will talk about our experience utilizing LSTM in multi-target tracking and show some intuitions about why the current LSTM may be insufficient for long-term multi-object tracking. A novel bilinear LSTM model suitable for multi-target tracking problems will be proposed, motivated by the classic recursive least squares formulation. Results on the MOT
2016 and MOT 2017 challenges will be shown that significantly outperform traditional LSTMs in terms of identity switches. In the second part, I will talk about PointConv, our recent work which efficiently implements CNN on irregularly spaced point cloud data. Experiment results on classification and semantic segmentation on point clouds will be shown that significantly improve over prior work.
Fuxin Li is an assistant professor in the School of Electrical Engineering and Computer Science at Oregon State University. His main research interests are deep learning, video object segmentation, multi-target tracking, point cloud deep networks, adversarial deep learning and human understanding of deep learning. Before OSU, he held research positions in University of Bonn and Georgia Institute of Technology. He obtained a Ph.D. degree from the Institute of Automation, Chinese Academy of Sciences, in 2009. He won an NSF CAREER award, (co-)won the PASCAL VOC semantic segmentation challenges from 2009-2012, and led a team to the 4th place finish in the DAVIS Video Segmentation challenge 2017. He has published more than 40 papers in computer vision, machine learning and natural language processing.
Wednesday, November 6, 2019 at 1:00pm to 2:00pm
Gleeson Hall (Chem Engr), 200
2115 SW Campus Way, Corvallis, OR 97331